acryl-datahub 0.15.0.6rc3__py3-none-any.whl → 1.0.0__py3-none-any.whl

datahub/metadata/schemas/IncidentInfo.avsc

@@ -108,7 +108,88 @@
       ],
       "name": "priority",
       "default": 0,
-      "doc": "A numeric severity or priority for the incident. On the UI we will translate this into something easy to understand."
+      "doc": "A numeric severity or priority for the incident. On the UI we will translate this into something easy to understand.\nCurrently supported: 0 - CRITICAL, 1 - HIGH, 2 - MED, 3 - LOW\n(We probably should have modeled as an enum)"
+    },
+    {
+      "type": [
+        "null",
+        {
+          "type": "array",
+          "items": {
+            "type": "record",
+            "name": "IncidentAssignee",
+            "namespace": "com.linkedin.pegasus2avro.incident",
+            "fields": [
+              {
+                "Searchable": {
+                  "addToFilters": true,
+                  "fieldName": "assignees",
+                  "filterNameOverride": "Assignee"
+                },
+                "java": {
+                  "class": "com.linkedin.pegasus2avro.common.urn.Urn"
+                },
+                "type": "string",
+                "name": "actor",
+                "doc": "The user or group assigned to the incident.",
+                "Urn": "Urn"
+              },
+              {
+                "type": {
+                  "type": "record",
+                  "name": "AuditStamp",
+                  "namespace": "com.linkedin.pegasus2avro.common",
+                  "fields": [
+                    {
+                      "type": "long",
+                      "name": "time",
+                      "doc": "When did the resource/association/sub-resource move into the specific lifecycle stage represented by this AuditEvent."
+                    },
+                    {
+                      "java": {
+                        "class": "com.linkedin.pegasus2avro.common.urn.Urn"
+                      },
+                      "type": "string",
+                      "name": "actor",
+                      "doc": "The entity (e.g. a member URN) which will be credited for moving the resource/association/sub-resource into the specific lifecycle stage. It is also the one used to authorize the change.",
+                      "Urn": "Urn"
+                    },
+                    {
+                      "java": {
+                        "class": "com.linkedin.pegasus2avro.common.urn.Urn"
+                      },
+                      "type": [
+                        "null",
+                        "string"
+                      ],
+                      "name": "impersonator",
+                      "default": null,
+                      "doc": "The entity (e.g. a service URN) which performs the change on behalf of the Actor and must be authorized to act as the Actor.",
+                      "Urn": "Urn"
+                    },
+                    {
+                      "type": [
+                        "null",
+                        "string"
+                      ],
+                      "name": "message",
+                      "default": null,
+                      "doc": "Additional context around how DataHub was informed of the particular change. For example: was the change created by an automated process, or manually."
+                    }
+                  ],
+                  "doc": "Data captured on a resource/association/sub-resource level giving insight into when that resource/association/sub-resource moved into a particular lifecycle stage, and who acted to move it into that specific lifecycle stage."
+                },
+                "name": "assignedAt",
+                "doc": "The time & actor responsible for assiging the assignee."
+              }
+            ],
+            "doc": "The incident assignee type.\nThis is in a record so that we can add additional fields if we need to later (e.g.\nthe type of the assignee."
+          }
+        }
+      ],
+      "name": "assignees",
+      "default": null,
+      "doc": "The parties assigned with resolving the incident"
     },
     {
       "type": {
@@ -135,7 +216,38 @@
               ]
             },
             "name": "state",
-            "doc": "The state of the incident"
+            "doc": "The top-level state of the incident, whether it's active or resolved."
+          },
+          {
+            "Searchable": {
+              "addToFilters": true,
+              "filterNameOverride": "Stage"
+            },
+            "type": [
+              "null",
+              {
+                "type": "enum",
+                "symbolDocs": {
+                  "FIXED": "The incident is in the resolved as completed stage.",
+                  "INVESTIGATION": "The incident root cause is being investigated.",
+                  "NO_ACTION_REQUIRED": "The incident is in the resolved with no action required state, e.g. the\nincident was a false positive, or was expected.",
+                  "TRIAGE": "The impact and priority of the incident is being actively assessed.",
+                  "WORK_IN_PROGRESS": "The incident is in the remediation stage."
+                },
+                "name": "IncidentStage",
+                "namespace": "com.linkedin.pegasus2avro.incident",
+                "symbols": [
+                  "TRIAGE",
+                  "INVESTIGATION",
+                  "WORK_IN_PROGRESS",
+                  "FIXED",
+                  "NO_ACTION_REQUIRED"
+                ]
+              }
+            ],
+            "name": "stage",
+            "default": null,
+            "doc": "The lifecycle stage for the incident - Null means no stage was assigned yet.\nIn the future, we may add CUSTOM here with a customStage string field for user-defined stages."
           },
           {
             "type": [
@@ -153,50 +265,7 @@
                 "fieldType": "COUNT"
               }
             },
-            "type": {
-              "type": "record",
-              "name": "AuditStamp",
-              "namespace": "com.linkedin.pegasus2avro.common",
-              "fields": [
-                {
-                  "type": "long",
-                  "name": "time",
-                  "doc": "When did the resource/association/sub-resource move into the specific lifecycle stage represented by this AuditEvent."
-                },
-                {
-                  "java": {
-                    "class": "com.linkedin.pegasus2avro.common.urn.Urn"
-                  },
-                  "type": "string",
-                  "name": "actor",
-                  "doc": "The entity (e.g. a member URN) which will be credited for moving the resource/association/sub-resource into the specific lifecycle stage. It is also the one used to authorize the change.",
-                  "Urn": "Urn"
-                },
-                {
-                  "java": {
-                    "class": "com.linkedin.pegasus2avro.common.urn.Urn"
-                  },
-                  "type": [
-                    "null",
-                    "string"
-                  ],
-                  "name": "impersonator",
-                  "default": null,
-                  "doc": "The entity (e.g. a service URN) which performs the change on behalf of the Actor and must be authorized to act as the Actor.",
-                  "Urn": "Urn"
-                },
-                {
-                  "type": [
-                    "null",
-                    "string"
-                  ],
-                  "name": "message",
-                  "default": null,
-                  "doc": "Additional context around how DataHub was informed of the particular change. For example: was the change created by an automated process, or manually."
-                }
-              ],
-              "doc": "Data captured on a resource/association/sub-resource level giving insight into when that resource/association/sub-resource moved into a particular lifecycle stage, and who acted to move it into that specific lifecycle stage."
-            },
+            "type": "com.linkedin.pegasus2avro.common.AuditStamp",
             "name": "lastUpdated",
             "doc": "The time at which the request was initially created"
           }
@@ -262,6 +331,21 @@
       "default": null,
       "doc": "The source of an incident, i.e. how it was generated."
     },
+    {
+      "Searchable": {
+        "/time": {
+          "fieldName": "startedAt",
+          "fieldType": "COUNT"
+        }
+      },
+      "type": [
+        "null",
+        "long"
+      ],
+      "name": "startedAt",
+      "default": null,
+      "doc": "The time at which the incident actually started (may be before the date it was raised)."
+    },
     {
       "Searchable": {
         "/time": {

datahub/metadata/schemas/InputFields.avsc

@@ -553,7 +553,9 @@
                                         "fieldName": "glossaryTerms",
                                         "fieldType": "URN",
                                         "filterNameOverride": "Glossary Term",
-                                        "hasValuesFieldName": "hasGlossaryTerms"
+                                        "hasValuesFieldName": "hasGlossaryTerms",
+                                        "includeSystemModifiedAt": true,
+                                        "systemModifiedAtFieldName": "termsModifiedAt"
                                       },
                                       "java": {
                                         "class": "com.linkedin.pegasus2avro.common.urn.GlossaryTermUrn"

datahub/metadata/schemas/MLFeatureKey.avsc

@@ -19,7 +19,8 @@
       "browsePathsV2",
       "structuredProperties",
       "forms",
-      "testResults"
+      "testResults",
+      "subTypes"
     ]
   },
   "name": "MLFeatureKey",

datahub/metadata/schemas/MLFeatureTableKey.avsc

@@ -19,7 +19,8 @@
       "browsePathsV2",
       "structuredProperties",
       "forms",
-      "testResults"
+      "testResults",
+      "subTypes"
     ]
   },
   "name": "MLFeatureTableKey",

datahub/metadata/schemas/MLModelDeploymentKey.avsc

@@ -11,7 +11,8 @@
       "deprecation",
       "globalTags",
       "dataPlatformInstance",
-      "testResults"
+      "testResults",
+      "container"
     ]
   },
   "name": "MLModelDeploymentKey",

datahub/metadata/schemas/MLModelGroupKey.avsc

@@ -18,7 +18,9 @@
       "browsePathsV2",
       "structuredProperties",
       "forms",
-      "testResults"
+      "testResults",
+      "subTypes",
+      "container"
     ]
   },
   "name": "MLModelGroupKey",

datahub/metadata/schemas/MLModelKey.avsc

@@ -30,7 +30,9 @@
       "structuredProperties",
       "forms",
       "testResults",
-      "versionProperties"
+      "versionProperties",
+      "subTypes",
+      "container"
     ]
   },
   "name": "MLModelKey",

datahub/metadata/schemas/MLPrimaryKeyKey.avsc

@@ -17,7 +17,8 @@
       "dataPlatformInstance",
       "structuredProperties",
       "forms",
-      "testResults"
+      "testResults",
+      "subTypes"
     ]
   },
   "name": "MLPrimaryKeyKey",

datahub/metadata/schemas/MetadataChangeEvent.avsc

@@ -183,6 +183,7 @@
                       },
                       {
                         "Searchable": {
+                          "boostScore": 10.0,
                           "enableAutocomplete": true,
                           "fieldNameAliases": [
                             "_entityName"
@@ -994,7 +995,9 @@
                                   "fieldName": "glossaryTerms",
                                   "fieldType": "URN",
                                   "filterNameOverride": "Glossary Term",
-                                  "hasValuesFieldName": "hasGlossaryTerms"
+                                  "hasValuesFieldName": "hasGlossaryTerms",
+                                  "includeSystemModifiedAt": true,
+                                  "systemModifiedAtFieldName": "termsModifiedAt"
                                 },
                                 "java": {
                                   "class": "com.linkedin.pegasus2avro.common.urn.GlossaryTermUrn"
@@ -1616,6 +1619,19 @@
                         "name": "countryCode",
                         "default": null,
                         "doc": "two uppercase letters country code. e.g.  US"
+                      },
+                      {
+                        "Searchable": {
+                          "fieldType": "BOOLEAN",
+                          "queryByDefault": false
+                        },
+                        "type": [
+                          "boolean",
+                          "null"
+                        ],
+                        "name": "system",
+                        "default": false,
+                        "doc": "Whether the corpUser is a system user."
                       }
                     ],
                     "doc": "Linkedin corp user information"
@@ -4644,7 +4660,9 @@
                                   "/terms/*/urn": {
                                     "boostScore": 0.5,
                                     "fieldName": "editedFieldGlossaryTerms",
-                                    "fieldType": "URN"
+                                    "fieldType": "URN",
+                                    "includeSystemModifiedAt": true,
+                                    "systemModifiedAtFieldName": "schemaFieldTermsModifiedAt"
                                   }
                                 },
                                 "type": [

datahub/metadata/schemas/PostKey.avsc

@@ -5,7 +5,8 @@
     "keyForEntity": "post",
     "entityCategory": "core",
     "entityAspects": [
-      "postInfo"
+      "postInfo",
+      "subTypes"
     ]
   },
   "name": "PostKey",

datahub/metadata/schemas/SchemaFieldKey.avsc

@@ -13,7 +13,8 @@
       "schemaFieldAliases",
       "documentation",
       "testResults",
-      "deprecation"
+      "deprecation",
+      "subTypes"
     ]
   },
   "name": "SchemaFieldKey",

datahub/metadata/schemas/SchemaMetadata.avsc

@@ -777,7 +777,9 @@
                                 "fieldName": "glossaryTerms",
                                 "fieldType": "URN",
                                 "filterNameOverride": "Glossary Term",
-                                "hasValuesFieldName": "hasGlossaryTerms"
+                                "hasValuesFieldName": "hasGlossaryTerms",
+                                "includeSystemModifiedAt": true,
+                                "systemModifiedAtFieldName": "termsModifiedAt"
                               },
                               "java": {
                                 "class": "com.linkedin.pegasus2avro.common.urn.GlossaryTermUrn"

datahub/metadata/schemas/StructuredPropertyDefinition.avsc

@@ -23,6 +23,13 @@
       "doc": "The display name of the property. This is the name that will be shown in the UI and can be used to look up the property id."
     },
     {
+      "UrnValidation": {
+        "entityTypes": [
+          "dataType"
+        ],
+        "exist": true,
+        "strict": true
+      },
       "java": {
         "class": "com.linkedin.pegasus2avro.common.urn.Urn"
       },
@@ -111,6 +118,13 @@
           "fieldName": "entityTypes"
         }
       },
+      "UrnValidation": {
+        "entityTypes": [
+          "entityType"
+        ],
+        "exist": true,
+        "strict": true
+      },
       "type": {
         "type": "array",
         "items": "string"

datahub/metadata/schemas/VersionProperties.avsc

@@ -137,6 +137,24 @@
       "name": "sortId",
       "doc": "Sort identifier that determines where a version lives in the order of the Version Set.\nWhat this looks like depends on the Version Scheme. For sort ids generated by DataHub we use an 8 character string representation."
     },
+    {
+      "type": {
+        "type": "enum",
+        "symbolDocs": {
+          "ALPHANUMERIC_GENERATED_BY_DATAHUB": "String managed by DataHub. Currently, an 8 character alphabetical string.",
+          "LEXICOGRAPHIC_STRING": "String sorted lexicographically."
+        },
+        "name": "VersioningScheme",
+        "namespace": "com.linkedin.pegasus2avro.versionset",
+        "symbols": [
+          "LEXICOGRAPHIC_STRING",
+          "ALPHANUMERIC_GENERATED_BY_DATAHUB"
+        ]
+      },
+      "name": "versioningScheme",
+      "default": "LEXICOGRAPHIC_STRING",
+      "doc": "What versioning scheme `sortId` belongs to.\nDefaults to a plain string that is lexicographically sorted."
+    },
     {
       "type": [
         "null",

datahub/metadata/schemas/VersionSetProperties.avsc

@@ -36,9 +36,14 @@
     {
       "type": {
         "type": "enum",
+        "symbolDocs": {
+          "ALPHANUMERIC_GENERATED_BY_DATAHUB": "String managed by DataHub. Currently, an 8 character alphabetical string.",
+          "LEXICOGRAPHIC_STRING": "String sorted lexicographically."
+        },
         "name": "VersioningScheme",
         "namespace": "com.linkedin.pegasus2avro.versionset",
         "symbols": [
+          "LEXICOGRAPHIC_STRING",
           "ALPHANUMERIC_GENERATED_BY_DATAHUB"
         ]
       },

datahub/pydantic/compat.py

@@ -0,0 +1,58 @@
+import functools
+from typing import Any, Callable, Optional, TypeVar, cast
+
+# Define a type variable for the decorator
+F = TypeVar("F", bound=Callable[..., Any])
+
+
+# Check which Pydantic version is installed
+def get_pydantic_version() -> int:
+    """Determine if Pydantic v1 or v2 is installed."""
+    try:
+        import pydantic
+
+        version = pydantic.__version__
+        return 1 if version.startswith("1.") else 2
+    except (ImportError, AttributeError):
+        # Default to v1 if we can't determine version
+        return 1
+
+
+PYDANTIC_VERSION = get_pydantic_version()
+
+
+# Create compatibility layer for dict-like methods
+def compat_dict_method(v1_method: Optional[Callable] = None) -> Callable:
+    """
+    Decorator to make a dict method work with both Pydantic v1 and v2.
+
+    In v1: Uses the decorated method (typically dict)
+    In v2: Redirects to model_dump with appropriate parameter mapping
+    """
+
+    def decorator(func: F) -> F:
+        @functools.wraps(func)
+        def wrapper(self, *args, **kwargs):
+            if PYDANTIC_VERSION >= 2:
+                # Map v1 parameters to v2 parameters
+                # exclude -> exclude
+                # exclude_unset -> exclude_unset
+                # exclude_defaults -> exclude_defaults
+                # exclude_none -> exclude_none
+                # by_alias -> by_alias
+                model_dump_kwargs = kwargs.copy()
+
+                # Handle the 'exclude' parameter differently between versions
+                exclude = kwargs.get("exclude", set())
+                if isinstance(exclude, (set, dict)):
+                    model_dump_kwargs["exclude"] = exclude
+
+                return self.model_dump(**model_dump_kwargs)
+            return func(self, *args, **kwargs)
+
+        return cast(F, wrapper)
+
+    # Allow use as both @compat_dict_method and @compat_dict_method()
+    if v1_method is None:
+        return decorator
+    return decorator(v1_method)

datahub/sdk/__init__.py

@@ -1,7 +1,7 @@
-import warnings
+import types
 
 import datahub.metadata.schema_classes as models
-from datahub.errors import ExperimentalWarning, SdkUsageError
+from datahub.errors import SdkUsageError
 from datahub.ingestion.graph.config import DatahubClientConfig
 from datahub.metadata.urns import (
     ChartUrn,
@@ -20,14 +20,32 @@ from datahub.metadata.urns import (
 from datahub.sdk.container import Container
 from datahub.sdk.dataset import Dataset
 from datahub.sdk.main_client import DataHubClient
+from datahub.sdk.search_filters import Filter, FilterDsl
 
-warnings.warn(
-    "The new datahub SDK (e.g. datahub.sdk.*) is experimental. "
-    "Our typical backwards-compatibility and stability guarantees do not apply to this code. "
-    "When it's promoted to stable, the import path will change "
-    "from `from datahub.sdk import ...` to `from datahub import ...`.",
-    ExperimentalWarning,
-    stacklevel=2,
-)
-del warnings
-del ExperimentalWarning
+# We want to print out the warning if people do `from datahub.sdk import X`.
+# But we don't want to print out warnings if they're doing a more direct
+# import like `from datahub.sdk.container import Container`, since that's
+# what our internal code does.
+_vars = {}
+for _name, _value in list(locals().items()):
+    if not _name.startswith("_") and (
+        _name == "models" or not isinstance(_value, types.ModuleType)
+    ):
+        _vars[_name] = _value
+        del locals()[_name]
+
+
+def __getattr__(name):
+    import warnings
+
+    from datahub.errors import ExperimentalWarning
+
+    warnings.warn(
+        "The new datahub SDK (e.g. datahub.sdk.*) is experimental. "
+        "Our typical backwards-compatibility and stability guarantees do not apply to this code. "
+        "When it's promoted to stable, the import path will change "
+        "from `from datahub.sdk import ...` to `from datahub import ...`.",
+        ExperimentalWarning,
+        stacklevel=2,
+    )
+    return _vars[name]

datahub/sdk/_all_entities.py

@@ -1,8 +1,8 @@
 from typing import Dict, List, Type
 
-from datahub.sdk._entity import Entity
 from datahub.sdk.container import Container
 from datahub.sdk.dataset import Dataset
+from datahub.sdk.entity import Entity
 
 # TODO: Is there a better way to declare this?
 ENTITY_CLASSES_LIST: List[Type[Entity]] = [

datahub/sdk/_attribution.py

@@ -5,6 +5,10 @@ from typing import Iterator
 
 from datahub.utilities.str_enum import StrEnum
 
+# TODO: This attribution setup is not the final form. I expect that once we have better
+# backend support for attribution and attribution-oriented patch, this will become a bit
+# more sophisticated.
+
 
 class KnownAttribution(StrEnum):
     INGESTION = "INGESTION"